Please use this identifier to cite or link to this item:
標題: 撓性關節雙機械臂之類神經網路控制
Neural Network Control of Dual Arm Robot with Flexible Joints
作者: 陳驛俊
Chen, Yi-Chun
關鍵字: neural network;類神經網路;dual-arm robot;flexible joints;雙機械臂;撓性關節
出版社: 機械工程學系所
引用: [1] L. M. Sweet and M. C. Good, “Redefinition on the robot motion control problem:effects of plant dynamics,drive system constraints,and user requirement” IEEE Conference on Decision and Control, pp. 724-732, 1984 [2] D. Li, J. W. Zu and A. A. Goldenberg, “Dynamic modeling and mode analysis of flexible-link, flexible-joint robots” Mechanism and Machine Theory, vol. 33, no. 7, pp. 1031-1044, Oct. 1998 [3] M. W. Spong, “Modeling and control of elastic joint robots” Journal of Dynamic Systems, Measurement and Control, Transactions of the ASME, vol. 109, no. 4, pp. 310-319, Dec. 1987 [4] N. Hogan, “Impedance Control: an Approach to Manipulation. Part I - Theory” ASME Journal of Dynamic Systems, Measurement, and Control, vol. 107, pp. 1-7 ,1985 [5] N. Hogan, “Impedance Control: an Approach to Manipulation. Part II - Implementation” ASME Journal of Dynamic Systems, Measurement, and Control, vol. 107, pp. 8-16,1985 [6] N. Hogan, “Impedance Control: an Approach to Manipulation. Part III - Application” ASME Journal of Dynamic Systems, Measurement, and Control, vol. 107, pp. 17-24,1985 [7] N. Hogan, “Stable Execution of Contact Tasks Using Impedance Control” IEEE International Conference on Robotics & Automation, vol. 2, pp. 1047-1054,1987 [8] Christian Ott, “On the Passivity-Based Impedance Control of Flexible Joint Robots” IEEE International Conference on Robotics and Automation, Page(s): 416 - 429, 2008 [9] M. T. Mason, “Compliance and Force Control for Computer Controlled Manipulators” IEEE Transaction on Systems, Man and Cybernetics , vol. SMC-11, pp. 418-432, 1981 [10] M. H. Raibert and J. J. Craig, “Hybrid Position/Force Control of Manipulators” ASME Journal of Dynamic Systems, Measurement, and Control, pp.126-133, 1981 [11] J.T. Wen and K. Kenneth, “Motion and force control of multiple robotic manipulators” Automatica, vol. 28, no. 4, pp. 729-743, 1992. [12] S. Ahmad, “Constrained motion (force/position) control of flexible joint robots” IEEE Transactions on Systems, Man and Cybernetics, vol. 23, no. 2, pp. 374-381, Mar.-Apr. 1993 [13] J. K. Mills and A. A. Goldenberg, “Force and Position Control of Manipulators During Constrained Motion Tasks” IEEE Trans. in Robotics and Automation, vol. 5,no. 4, pp. 30-46 , Feb. 1989 [14] N. H. McClamroch and D. Wang, “Feedback Stabilization and Tracking of Constrained Robots” IEEE Transaction on Automatic Control, vol. 33, no. 5, pp. 419-426, May. 1988 [15] K. P. Jankowski and H. Van Brussel, “Inverse dynamics task control of flexible joint robots - I continuous-time approach” Mechanism and Machine Theory, vol. 28, no. 6, pp. 741-749, Nov. 1993 [16] J. Wittenburg, “Nonlinear Equations of Motion for Arbitary System of Interconnected Rigid Bodies” Symposium on the Dynamics of Multibody System, Munich, Germany, Pro. Published by Spring-Verlag, K. Magnus, editor , 1987 [17] J. Wittenburg and U. Wolz, “MESA VERGE: A Symbolic Program for Nonlinear Articulater Rigid Body Dynamics” ASME Design Engineering Technical Conference, 1985 [18] Erbatur, K.; Vinter, R.B.; Kaynak, O., “Feedback linearization control for a 3-DOF flexible joint elbow manipulator” IEEE Transactions on Systems, Man and Cybernetics, Page(s): 2979 - 2984 vol.4, 1994 [19] Isidori, A. 1985. “Nonlinear Control Systems: An introduction” New York: Springer-Verlag [20] Meng, Q.H.M. and Yao, Y.Y., 1994, “Design of Neural Network Controller for Robots Using Regressor Dynamics” Proc. of IEEE International Conference on Neural Networks, Vol 5, pp. 2743-2748 [21] Fukuda, T., Shibata, T., Tokita, M. and Mitsuoka, T., 1992, “Neuromophic Control: Adaptation and Learning” IEEE Transactions on Industrial Electronics, Vol. 39, No. 6, pp.21-27 [22] Okuma, S., Ishiguro, A., Furuhashi, T., Uchikawa, Y., 1990, “A Neural Network Compensator for Uncertainties of Robots Manipulators” Proc. of IEEE Conference on Decision and Control, pp. 3303-3308 [23] Yegerlehner, J.D. and Meckl, P.H., 1992, “Neural Network Control for a Two-Link Manipulator Undergoing Large Payload Changes” ASME Neural Networks in Manufacturing and Robotics, PED-Vol. 57, pp. 105-116
本文以平面撓性關節雙機械臂運用控制Lagrange Multiplier間接達到力量控制的觀念,進行位置與力量控制。雙機械臂系統在挾持物件時,我們視為閉鏈的多體機械系統,以切體法切開,應用Lagrange Multiplier定理,將系統的拘束方程式引入動態方程式中,建立拘束動態方程式。上述拘束動態方程式為一非線性系統,因此我們利用回饋線性化法將拘束動態方程式線性化後進行控制。經由求解拘束動態方程式,可以求得Lagrange Multipliers,經由轉換計算,我們可由求得的Lagrange Multipliers計算出物件的受力,進行力量控制。為了解決系統參數不確定的問題,當控制器參數與機械臂真實參數有誤差時,我們將利用類神經網路對控制器的輸出做補償與修正。由電腦數值模擬的結果得知,經由類神經網路的補償與修正,在有系統參數誤差的情況下,對雙機械臂進行位置與力量控制亦可達到良好的控制效果。

This thesis presents position and force control scheme for dual-arm robots with flexible joints. Dual-arm robots holding an object can be seen as a closed chain multibody mechanical system. The cut-body method can be used to convert the system into two open chain systems. The Lagrange Multiplier theorem is used to derive a Lagrange Multiplier form of equation of motion. Solving the dynamic equations, we can get the Lagrange Multipliers, which can be used to calculate the force acting on the object held by dual-arm robots. Because the dynamic equation is a nonlinear equation, the feedback linearization method is used to linearize the dynamic equation to achieve the control object. To overcome the problem of uncertain parameter, the neural network is used to compensate the error caused by parameter uncertainties. From the computer simulation results, when the parameter error occurs, we could obtain the good control effects of dual arm robot systems with flexible joints.
其他識別: U0005-2607201117201200
Appears in Collections:機械工程學系所

Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.